Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification

Abstract

Correctly identifying sleep stages is important in diagnosing and treating sleep disorders. This paper proposes a joint classification-and-prediction framework based on convolutional neural networks (CNNs) for automatic sleep staging, and, subsequently, introduces a simple yet efficient CNN architecture to power the framework. Given a single input epoch, the novel framework jointly determines its label (classification) and its neighboring epochs' labels (prediction) in the contextual output. While the proposed framework is orthogonal to the widely adopted classification schemes, which take one or multiple epochs as contextual inputs and produce a single classification decision on the target epoch, we demonstrate its advantages in several ways. First, it leverages the dependency among consecutive sleep epochs while surpassing the problems experienced with the common classification schemes. Second, even with a single model, the framework has the capacity to produce multiple decisions, which are essential in obtaining a good performance as in ensemble-of-models methods, with very little induced computational overhead. Probabilistic aggregation techniques are then proposed to leverage the availability of multiple decisions. To illustrate the efficacy of the proposed framework, we conducted experiments on two public datasets: Sleep-EDF Expanded (Sleep-EDF), which consists of 20 subjects, and Montreal Archive of Sleep Studies (MASS) dataset, which consists of 200 subjects. The proposed framework yields an overall classification accuracy of 82.3% and 83.6%, respectively. We also show that the proposed framework not only is superior to the baselines based on the common classification schemes but also outperforms existing deep-learning approaches. To our knowledge, this is the first work going beyond the standard single-output classification to consider multitask neural networks for automatic sleep staging. This framework provides avenues for further studies of different neural-network architectures for automatic sleep staging.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 63

1. 1.

   Krieger A. C., Ed., Social and Economic Dimensions of Sleep Disorders, an Issue of Sleep Medicine Clinics. New York, NY, USA: Elsevier, 2017.

   Not in our library

2. 2.

   Redmond S. J. and Heneghan C., “Cardiorespiratory-based sleep staging in subjects with obstructive sleep apnea,” IEEE Trans. Biomed. Eng., vol. 53, no. 3, pp. 485–496, Mar. 2006.

   Not in our library10.1109/tbme.2005.869773

3. 3.

   Aboalayon K. A. I. et al., “Sleep stage classification using EEG signal analysis: A comprehensive survey and new investigation,” Entropy, vol. 18, no. 9, 2016, Art. no..

   Not in our library

4. 4.

   Kelly J. M. et al., “Recent developments in home sleep-monitoring devices,” ISRN Neurol., vol. 2012, 2012, Art. no..

   Not in our library10.5402/2012/768794

5. 5.

   Krakovská A. and Mezeiová K., “Automatic sleep scoring: A search for an optimal combination of measures,” Artif. Intell. Med., vol. 53, no. 1, pp. 25–33, 2011.

   Not in our library10.1016/j.artmed.2011.06.004

6. 6.

   Koley B. and Dey D., “An ensemble system for automatic sleep stage classification using single channel EEG signal,” Comput. Biol. Med., vol. 42, no. 12, pp. 1186–95, 2012.

   Not in our library10.1016/j.compbiomed.2012.09.012

7. 7.

   Phan H. et al., “Metric learning for automatic sleep stage classification,” in Proc. IEEE Eng. Med. Biol. Society, 2013, pp. 5025–5028.

   Not in our library10.1109/embc.2013.6610677

8. 8.

   Susmakova K. and Krakovska A., “Discrimination ability of individual measures used in sleep stages classification,” Artif. Intell. Med., vol. 44, pp. 261–277, 2008.

   Not in our library10.1016/j.artmed.2008.07.005

9. 9.

   Fell J. et al., “Discrimination of sleep stages: A comparison between spectral and nonlinear eeg measures,” Electroencephalography Clin. Neurophysiol., vol. 98, no. 5, pp. 401–10, 1996.

   Not in our library10.1016/0013-4694(96)95636-9

10. 10.

    Kim D. J. et al., “An estimation of the first positive Lyapunov exponent of the EEG in patients with schizophrenia,” Psychiatry Res., vol. 98, no. 3, pp. 177–89, 2000.

    Not in our library10.1016/s0925-4927(00)00052-4

11. 11.

    Lee J. M. et al., “Detrended fluctuation analysis of EEG in sleep apnea using MIT/BIH polysomnography data,” Comput. Biol. Med., vol. 32, pp. 37–47, 2012.

    Not in our library10.1016/s0010-4825(01)00031-2

12. 12.

    Zhang X.-S. et al., “EEG complexity as a measure of depth of anesthesia for patients,” IEEE Trans. Biomed. Eng., vol. 48, no. 12, pp. 1424–1433, Dec. 2001.

    Not in our library10.1109/10.966601

13. 13.

    Alickovic E. and Subasi A., “Ensemble SVM method for automatic sleep stage classification,” IEEE Trans. Instrum. Meas., vol. 67, no. 6, pp. 1258–1265, Jun. 2018.

    Not in our library

14. 14.

    Memar P. and Faradji F., “A novel multi-class EEG-based sleep stage classification system,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 6, no. 1, pp. 84–95, Jan. 2018.

    Not in our library10.1109/tnsre.2017.2776149

15. 15.

    Boostania R. et al., “A comparative review on sleep stage classification methods in patients and healthy individuals,” Comput. Methods Programs Biomed., vol. 140, pp. 77–91, 2017.

    Not in our library10.1016/j.cmpb.2016.12.004

16. 16.

    Imtiaz S. A. and Rodriguez-Villegas E., “Automatic sleep staging using state machine-controlled decision trees,” in Proc. IEEE Eng. Med. Biol. Society, 2015, pp. 378–381.

    Not in our library10.1109/embc.2015.7318378

17. 17.

    Stephansen J. B. et al., “The use of neural networks in the analysis of sleep stages and the diagnosis of narcolepsy,” 2017, arXiv:1710.02094.

    Not in our library

18. 18.

    Mikkelsen K. and Vos M. De, “Personalizing deep learning models for automatic sleep staging,” 2018, arXiv:1801.02645.

    Not in our library

19. 19.

    Zhang J. and Wu Y., “A new method for automatic sleep stage classification,” IEEE Trans. Biomed. Circuits Syst., vol. 11, no. 5, pp. 1097–1110, Oct. 2017.

    Not in our library10.1109/tbcas.2017.2719631

20. 20.

    Tsinalis O. et al., “Automatic sleep stage scoring with single-channel EEG using convolutional neural networks,” 2016, arXiv:1610.01683.

    Not in our library

21. 21.
    Automatic Sleep Stage Scoring Using Time-Frequency Analysis and Stacked Sparse Autoencoders · 2015

    No notice
22. 22.

    Supratak A. et al., “Deepsleepnet: A model for automatic sleep stage scoring based on raw single-channel EEG,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 25, no. 11, pp. 1998–2008, Nov. 2017.

    Not in our library10.1109/tnsre.2017.2721116

23. 23.

    Dong H. et al., “Mixed neural network approach for temporal sleep stage classification,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 26, no. 2, pp. 324–333, Feb. 2017.

    Not in our library10.1109/tnsre.2017.2733220

24. 24.

    Phan H. et al., “DNN filter bank improves 1-max pooling CNN for single-channel EEG automatic sleep stage classification,” in Proc. IEEE Eng. Med. Biol. Society, 2018.

    Not in our library10.1109/embc.2018.8512286

25. 25.

    Phan H. et al., “Automatic sleep stage classification using single-channel EEG: Learning sequential features with attention-based recurrent neural networks,” in Proc. IEEE Eng. Med. Biol. Society, 2018.

    Not in our library10.1109/embc.2018.8512480

26. 26.
    Deep learning · 2015

    No notice
27. 27.

    Lecun Y., “Generalization and network design strategies,” in Connectionism in Perspective. New York, NY, USA: Elsevier, 1989.

    Not in our library

28. 28.

    Längkvist M. et al., “Sleep stage classification using unsupervised feature learning,” Adv. Artif. Neural Syst., vol. 2012, pp. 1–9, 2012.

    Not in our library

29. 29.

    Hochreiter S. and Schmidhuber J., “Long short-term memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997.

    Not in our library10.1162/neco.1997.9.8.1735

30. 30.

    Koch P. et al., “Recurrent neural network based early prediction of future hand movements,” in Proc. IEEE Eng. Med. Biol. Society, 2018.

    Not in our library10.1109/embc.2018.8513145

31. 31.

    Koch P. et al., “Recurrent neural networks with weighting loss for early prediction of hand movements,” in Proc. Eur. Signal Process. Conf., 2018.

    Not in our library

32. 32.

    Ansari A. H. et al., “Neonatal seizure detection using deep convolutional neural networks,” Int. J. Neural Syst., vol. 28, 2018, Art. no..

    Not in our library10.1142/s0129065718500119

33. 33.

    Iber C. et al., “The AASM manual for the scoring of sleep and associated events: Rules, terminology and technical specifications,” Amer. Acad. Sleep Med., 2007.

    Not in our library

34. 34.

    Liang S.-F. et al., “A rule-based automatic sleep staging method,” in Proc. IEEE Eng. Med. Biol. Society, 2011, pp. 6067–6070.

    Not in our library10.1109/iembs.2011.6091499

35. 35.

    Sousa T. et al., “A two-step automatic sleep stage classification method with dubious range detection,” Comput. Biol. Med., vol. 59, pp. 42–53, 2015.

    Not in our library10.1016/j.compbiomed.2015.01.017

36. 36.

    O’Reilly C. et al., “Montreal archive of sleep studies: An open-access resource for instrument benchmarking & exploratory research,” J. Sleep Res., vol. 23, pp. 628–635, 2014.

    Not in our library10.1111/jsr.12169

37. 37.

    Chambon S. et al., “A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 26, no. 4, pp. 758–769, Apr. 2018.

    Not in our library10.1109/tnsre.2018.2813138

38. 38.

    Andreotti F. et al., “Multichannel sleep stage classification and transfer learning using convolutional neural networks,” in Proc. IEEE Eng. Med. Biol. Society, 2018.

    Not in our library10.1109/embc.2018.8512214

39. 39.

    Hinton G. et al., “Distilling the knowledge in a neural network,” in Proc. NIPS 2014 Deep Learn. Represent. Learn. Workshop, 2014.

    Not in our library

40. 40.

    Dietterich T. G., “Ensemble methods in machine learning,” in Multiple Classifier Systems. Berlin, Germany: Springer, 2000, pp. 1–15.

    Not in our library

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.